WeKnora integrates three strategies of keyword retrieval, vector retrieval and knowledge graph retrieval, allowing users to use them in free combination. This hybrid retrieval mechanism can match document content from multiple dimensions, significantly improving the accuracy of information recall. For example, when searching for technical documents, keyword search locates technical terms, vector search captures semantic relevance, and knowledge graph mines logical relationships between entities. The system also supports docking Elasticsearch and other mainstream vector databases to further optimize retrieval efficiency.
This answer comes from the articleWeKnora: Tencent's out-of-the-box enterprise-level Q&A knowledge baseThe
May not be reproduced without permission:AI productivity tools " WeKnora Uses Hybrid Search Strategy to Improve Result Accuracy
